© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 40657
    Prev
    Next
    INDEX
    Explanations

    references to astronomical objects, specifically black holes and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    319
    -0.06
    omo
    -0.06
    greg
    -0.06
     Fet
    -0.06
     succes
    -0.06
    éĻ£
    -0.06
    inch
    -0.06
     Eph
    -0.05
     Teams
    -0.05
    .fi
    -0.05
    POSITIVE LOGITS
    ucher
    0.08
     gal
    0.07
     Galaxy
    0.07
     galaxy
    0.07
     Milky
    0.07
    _gc
    0.07
    ÑĢид
    0.07
    rnd
    0.07
    spir
    0.07
    _GC
    0.07
    Activations Density 0.088%

    No Known Activations